© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 98968
    Prev
    Next
    INDEX
    Explanations

    beginning of something

    np_acts-logits-general · gemini-2.5-flash-lite

    the beginning of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     on
    0.86
     drugi
    0.78
     it
    0.76
     have
    0.75
     thereon
    0.69
     accommodate
    0.68
     appear
    0.66
    ד
    0.66
    、
    0.65
     are
    0.64
    POSITIVE LOGITS
    is
    0.71
    r
    0.70
    semester
    0.67
    sets
    0.63
    आती
    0.61
    rand
    0.61
    kost
    0.59
    spolit
    0.59
    tter
    0.57
    cobra
    0.57
    Activations Density 0.103%

    No Known Activations